Korean J Radiol.  2025 Apr;26(4):304-312. 10.3348/kjr.2024.1161.

Adherence of Studies on Large Language Models for Medical Applications Published in Leading Medical Journals According to the MI-CLEAR-LLM Checklist

• Ko JS
• Heo H
• Suh CH
• Yi J
• Shim WH

• KMID: 2566225
• DOI: http://doi.org/10.3348/kjr.2024.1161

Abstract

Objective
To evaluate the adherence of large language model (LLM)-based healthcare research to the Minimum Reporting Items for Clear Evaluation of Accuracy Reports of Large Language Models in Healthcare (MI-CLEAR-LLM) checklist, a framework designed to enhance the transparency and reproducibility of studies on the accuracy of LLMs for medical applications.
Materials and Methods
A systematic PubMed search was conducted to identify articles on LLM performance published in high-ranking clinical medicine journals (the top 10% in each of the 59 specialties according to the 2023 Journal Impact Factor) from November 30, 2022, through June 25, 2024. Data on the six MI-CLEAR-LLM checklist items: 1) identification and specification of the LLM used, 2) stochasticity handling, 3) prompt wording and syntax, 4) prompt structuring, 5) prompt testing and optimization, and 6) independence of the test data—were independently extracted by two reviewers, and adherence was calculated for each item.
Results
Of 159 studies, 100% (159/159) reported the name of the LLM, 96.9% (154/159) reported the version, and 91.8% (146/159) reported the manufacturer. However, only 54.1% (86/159) reported the training data cutoff date, 6.3% (10/159) documented access to web-based information, and 50.9% (81/159) provided the date of the query attempts. Clear documentation regarding stochasticity management was provided in 15.1% (24/159) of the studies. Regarding prompt details, 49.1% (78/159) provided exact prompt wording and syntax but only 34.0% (54/159) documented prompt-structuring practices. While 46.5% (74/159) of the studies detailed prompt testing, only 15.7% (25/159) explained the rationale for specific word choices. Test data independence was reported for only 13.2% (21/159) of the studies, and 56.6% (43/76) provided URLs for internet-sourced test data.
Conclusion
Although basic LLM identification details were relatively well reported, other key aspects, including stochasticity, prompts, and test data, were frequently underreported. Enhancing adherence to the MI-CLEAR-LLM checklist will allow LLM research to achieve greater transparency and will foster more credible and reliable future studies.

Keyword

Large language model; Large multimodal model; Chatbot; Generative; Artificial intelligence; Deep learning; Reporting; Guideline; Checklist; Standard; Adherence; Quality